Browsing by Author "Huang, YH"

Now showing 1 - 5 of 5

Applying two-stage XCS model on global overnight effect local stock prediction
(2005)
Chen, AP
;
Chen, YC
;
Huang, YH
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
This study applied an integrated artificial intelligence method, extend learning classifier system (XCS), to predict the stock trend fluctuation considering the global overnight effect. However, some researchers have already indicated that XCS model that is applied successfully to form a forecast model in local market. Based on those prediction models, we put more effort to focus on the financial phenomenon, overnight effect between each two global markets, and we developed a two-stage XCS model to forecast the local stock market. In the experiments, DJi and Twi are chosen as referent and predicted markets respectively, and the model is trained by their historical data. For its accuracy verified, the model is tested by recently data. Finally, we have concluded that the proposed model successfully simulates the phenomenon, and the high ratio of correctness is definitely figured out.
Effect of Fe2+ on catalytic oxidation in a fluidized bed reactor
(1999-11-01)
Chou, SS
;
Huang, CP
;
Huang, YH
;
環境工程研究所
;
Institute of Environmental Engineering
The aim of this study was to investigate the effect of Fe2+ on the catalytic oxidation in the fluidized-bed reactor (FBR) applying supported gamma-FeOOH as the carrier. Processes without Fe2+ addition and with Fe2+ addition (FBR-Fenton method) were performed on the oxidation of benzoic acid (BA) by H2O2. When Fe2+ was not added in the FBR, the high COD removal at low pH was caused by homogeneous catalysis of Fe2+ formed via reductive dissolution of gamma-FeOOH. In the FBR-Fenton process, both mineralization of organics and crystallization of Fe(III) were simultaneously well performed under adequate condition. The reaction mechanism, including the reductive dissolution and crystallization of gamma-FeOOH as well as the oxidation of BA, was proposed based on the experimental results. (C)1999 Elsevier Science Ltd. All rights reserved.
Heterogeneous and homogeneous catalytic oxidation by supported gamma-FeOOH in a fluidized bed reactor: Kinetic approach
(2001-03-15)
Chou, SS
;
Huang, CP
;
Huang, YH
;
環境工程研究所
;
Institute of Environmental Engineering
Oxidation of benzoic,acid (BA) by H2O2 was performed with a never supported gamma -FeOOH catalyst in a circulating fluidized-bed reactor (CFBR).; This study focused mainly on determining the proportions of homogeneous catalysis and heterogeneous catalysis in this CFBR. Also studied herein was how pH, H2O2 concentration, and BA concentration affect the oxidation of BA. Experimental results indicate that the decomposition rate of H2O2 was proportional to its concentration and that the oxidation rate of BA depended on both H2O2 and BA concentrations. The change in the rate constant of heterogeneous catalysis by pH was described in terms of ionization fractions of surface hydroxyl group. From the mathematical deduction, we-can infer that the reaction rate associated with equivalent toF(III)OH(2)(+) is markedly higher than that with equivalent toF(III)OH. Conclusively, although heterogeneous catalysis contributes primarily to the oxidation of BA at pH 4.4-7.0, the homogeneous catalysis is of increasing importance below pH 4.4 because of the reductive dissolution of gamma -FeOOH.
The construction of production performance prediction system for semiconductor manufacturing with artificial neural networks
(1999-04-15)
Huang, CL
;
Huang, YH
;
Chang, TY
;
Chang, SH
;
Chung, CH
The major performance measurements for wafer fabrication system comprise WIP level, throughput and cycle time. These measurements are influenced by various factors, including machine breakdown, operator absence, poor dispatching rules, emergency order and material shortage. Generally, production managers use the WIP level profile of each stage to identify an abnormal situation, and then make corrective actions. However, such a measurement is reactive, not proactive. Proactive actions must effectively predict the future performance, analyze the abnormal situation, and then generate corrective actions to prevent performance from degrading. This work systematically constructs artificial neural network models to predict production performances for a semiconductor manufacturing factory. An application for a local DRAM wafer fabrication has demonstrated the accuracy of neural network models in predicting production performances.
Treatment of high strength hexamine-containing wastewater by Electro-Fenton method
(1999-02-01)
Chou, SS
;
Huang, YH
;
Lee, SN
;
Huang, GH
;
Huang, CP
A novel Electro-Fenton (EF-Fere) method, applied H2O2 and electrogenerated ferrous ion, was investigated for treating the hexamine-containing wastewater. The performance of Fe2+ generation in the electrolytic system was first evaluated, including the factors of the cathode material, initial pH, initial ferric concentration (Fe-i), and current density. When initial pH exceeded 2.5, the current efficiency dramatically decreased, which was due to the formation of Fe(OH)(3). Between 3000 and 10,000 mg/l of Fe-i, the initial current efficiency of Fe2+ generation was almost constant (85-87%), which dropped sharply to 39% at 1000 mg/l. In EF-Fere experiments, the COD removal efficiency attained above 94% after 5 h of reaction. The relationship between the temperature, dissolved oxygen, and COD was discussed. The changes in hexamine and its oxidation intermediates (methanol, formaldahyde, formate, ammonium and nitrate) during the reaction were also investigated. Three additional experiments using H2O2/Fe2+, H2O2/Fe3+, and direct electrolysis were also conducted to treat the hexamine-containing wastewater for comparison. The results showed that the EF-Fere method was the most efficient. (C) 1998 Elsevier Science Ltd. All rights reserved.